MiniMax H3 Open Weights | Try in Video Generator →
Home/Explore/Alibaba/Wan 2.2/I2v Plus 480p

Wan 2.2 I2V Plus 480P | Fast Image-to-Video API

alibaba/

WAN 2.2 i2v-plus-480p turns images into unlimited AI videos at 480p via image-to-video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Input

Idle

$0.2per run·~50 / $10

Next:

ExamplesView all

A bearded backpacker, around 30 years old, sits on a rock at a mountain summit, looking out over a sea of clouds and distant mountain ranges. The first light of sunrise is just breaking, painting the sky in shades of orange and pink. He is wearing a windproof jacket, with his trekking pole and backpack placed beside him. He takes a sip of hot tea from a thermos, a look of contentment and peace on his face. The camera slowly pushes in from behind him, moving over his shoulder to reveal the majestic view before him.

A young female potter, her hands covered in wet clay, is shaping a vase on a rapidly spinning potter's wheel. Her gaze is highly concentrated, and the muscles in her arms tense subtly as the vessel takes form. Her studio is filled with various unfinished pieces and jars of glaze. Sunlight streams through a dusty window, making the airborne dust particles visible. The entire scene is rich with the texture of craftsmanship and the quiet beauty of the creative process.

A female data analyst inside a control room filled with holographic screens and futuristic interfaces. She has sleek, silver short hair and a sharp, focused gaze. She wears a form-fitting, dark gray jumpsuit with clean, simple lines. Her fingers move swiftly through the air, interacting with a 3D data star map floating in front of her. The surrounding environment is dimly lit, with only the blue and white light from the data displays illuminating her face and hands, creating a high-tech and mysterious atmosphere.

An elderly librarian, wearing reading glasses, is carefully wiping the leather cover of an ancient book with a soft cloth. Afternoon sunlight streams through the tall library windows, creating distinct beams of light. The air is filled with the scent of old paper and wood. His movements are slow and full of reverence, his face showing a deep appreciation for knowledge. This is an extremely quiet close-up shot, focusing on the details of his hands and the interplay of light and shadow.

Related Models

README

WAN 2.2 Image-to-Video Plus (480p)

The WAN 2.2 I2V-Plus model is a state-of-the-art image-to-video generator available on Cloud's DashScope platform. It uses an innovative Mixture of Experts (MoE) architecture to create smooth and realistic videos from static images at a 480p resolution. This model is designed for short, high-quality clips.

Why it looks great

  • MoE architecture: dynamically directs tasks to specialized experts for improved detail and motion accuracy.
  • Natural motion synthesis: creates smooth and realistic transitions from a still image.
  • Detail preservation: keeps sharp textures and clear faces in dynamic shots.
  • Temporal stability: reduces flicker and frame inconsistencies.
  • Optimized for portraits: excels at transforming human photos into realistic talking or moving videos.

Limits and Performance

  • Output resolution: fixed at 480p
  • Max clip length per job: 5 seconds
  • Processing speed: ~5–10 seconds of wall time per second of video (varies by queue and complexity)

Pricing

Output ResolutionCost per 5 secondsMax Length
480p$0.205 seconds

Billing Rules

  • Minimum charge = 5 seconds (one clip)
  • No partial billing — all jobs are billed as a 5-second generation
  • Total cost = number of clips × $0.20

How to Use

  1. Upload a source image (clear, high-quality recommended).
  2. (Optional) Add a prompt to guide motion or scene style.
  3. Select output length (5 seconds).
  4. Run the job and download the 480p video.

Notes

  • This version only supports 480p and up to 5 seconds per clip.
  • For longer or higher-resolution outputs, check newer WAN versions (WAN 2.5).
Note:This website uses AI models provided by third parties.

Wan 2.2 I2v Plus 480p API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Wan 2.2 I2v Plus 480p below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "enable_prompt_expansion": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "duration": 5,
        "enable_prompt_expansion": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "duration": 5,
    "enable_prompt_expansion": False,
    "seed": -1
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Wan 2.2 I2v Plus 480p API — Frequently asked questions

What is the Wan 2.2 I2v Plus 480p API?

Wan 2.2 I2v Plus 480p is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.2 i2v-plus-480p turns images into unlimited AI videos at 480p via image-to-video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Wan 2.2 I2v Plus 480p API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-2.2-i2v-plus-480p.

How much does Wan 2.2 I2v Plus 480p cost per run?

Wan 2.2 I2v Plus 480p starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan 2.2 I2v Plus 480p accept?

Key inputs: `prompt`, `image`, `duration`, `seed`, `negative_prompt`, `enable_prompt_expansion`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-2.2-i2v-plus-480p.

How do I get started with the Wan 2.2 I2v Plus 480p API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Wan 2.2 I2v Plus 480p outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Wan 2.2 I2V Plus 480P | Fast Image-to-Video API on WaveSpeedAI